src/java/org/apache/nutch/service/impl/SequenceReader.java (6 lines): - line 44: // TODO Auto-generated method stub - line 65: // TODO Auto-generated catch block - line 77: // TODO Auto-generated method stub - line 101: // TODO Auto-generated catch block - line 136: // TODO Auto-generated catch block - line 163: // TODO Auto-generated catch block src/java/org/apache/nutch/indexer/CleaningJob.java (3 lines): - line 108: // // TODO updateRequest.process(solr); - line 131: // // TODO updateRequest.process(solr); - line 132: // // TODO updateRequest = new UpdateRequest(); src/java/org/apache/nutch/parse/ParseOutputFormat.java (3 lines): - line 420: //FIXME: toDomain will never be null, correct? - line 437: //FIXME: toDomain will never be null, correct? - line 443: //FIXME: toDomain will never be null, correct? src/java/org/apache/nutch/tools/WARCUtils.java (2 lines): - line 80: record.addLabelValue(ROBOTS, "classic"); // TODO Make configurable? - line 213: // TODO: http/2 src/plugin/indexer-solr/src/java/org/apache/nutch/indexwriter/solr/SolrIndexWriter.java (2 lines): - line 142: // TODO: 1/08/17 Implement this - line 146: // TODO: 1/08/17 Implement this src/plugin/indexer-rabbit/src/java/org/apache/nutch/indexwriter/rabbit/RabbitIndexWriter.java (1 line): - line 212: commit(); //TODO: This is because indexing job never call commit method. It should be fixed. src/plugin/urlfilter-validator/src/java/org/apache/nutch/urlfilter/validator/UrlValidator.java (1 line): - line 263: // TODO: Rewrite to use ArrayList and .add semantics: see VALIDATOR-203 src/plugin/protocol-interactiveselenium/src/java/org/apache/nutch/protocol/interactiveselenium/HttpResponse.java (1 line): - line 481: // TODO: (CM) We don't know the header names here src/plugin/urlmeta/src/java/org/apache/nutch/indexer/urlmeta/URLMetaIndexingFilter.java (1 line): - line 61: * TODO: It may be ideal to offer two separate properties, to specify what gets src/java/org/apache/nutch/tools/arc/ArcRecordReader.java (1 line): - line 306: // TODO: It would be best to start at the end of the gzip read but src/java/org/apache/nutch/tools/arc/ArcSegmentCreator.java (1 line): - line 333: // the arc file, TODO: currently this doesn't handle text of errors src/java/org/apache/nutch/parse/HtmlParseFilters.java (1 line): - line 60: // TODO: What happens when parseResult.isEmpty() ? src/plugin/protocol-http/src/java/org/apache/nutch/protocol/http/HttpResponse.java (1 line): - line 623: // TODO: (CM) We don't know the header names here src/plugin/index-metadata/src/java/org/apache/nutch/indexer/metadata/MetadataIndexer.java (1 line): - line 119: // TODO check conflict between field names e.g. could have same label src/java/org/apache/nutch/parse/ParserFactory.java (1 line): - line 114: // TODO once the MimeTypes is available src/java/org/apache/nutch/tools/CommonCrawlDataDumper.java (1 line): - line 376: //TODO: Make this Jackson Format implementation reusable ivy/ivy.xml (1 line): - line 133: src/java/org/apache/nutch/hostdb/UpdateHostDbMapper.java (1 line): - line 160: * TODO: fix multi redirects: host_a => host_b/page => host_c/page/whatever src/java/org/apache/nutch/util/URLUtil.java (1 line): - line 298: // TODO : handle ipv6 src/plugin/protocol-httpclient/src/java/org/apache/nutch/protocol/httpclient/HttpAuthenticationFactory.java (1 line): - line 90: // TODO Add additional Authentication lookups here src/plugin/protocol-htmlunit/src/java/org/apache/nutch/protocol/htmlunit/HttpResponse.java (1 line): - line 546: // TODO: (CM) We don't know the header names here src/java/org/apache/nutch/tools/CommonCrawlConfig.java (1 line): - line 52: // TODO init(this.getClass().getResourceAsStream("CommonCrawlConfig.properties")); src/plugin/protocol-selenium/src/java/org/apache/nutch/protocol/selenium/HttpResponse.java (1 line): - line 431: // TODO: (CM) We don't know the header names here src/java/org/apache/nutch/crawl/AdaptiveFetchSchedule.java (1 line): - line 138: // TODO: Maybe add host validatio here? src/plugin/scoring-similarity/src/java/org/apache/nutch/scoring/similarity/cosine/Model.java (1 line): - line 72: // TODO : Allow for corpus of documents to be provided as gold standard. src/java/org/apache/nutch/service/impl/ServiceWorker.java (1 line): - line 44: // TODO Auto-generated catch block src/plugin/feed/src/java/org/apache/nutch/parse/feed/FeedParser.java (1 line): - line 342: // TODO: What to do if contents.size() > 1?